Paper Citation Record · LEDGER

Large Language Models Often Know When They Are Being Evaluated

As of 22 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 43 inbound Pith citation observations for arXiv:2505.23836.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.23836 v3

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:16:16.539220Z

measured 56 of 56 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 43 of 43 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:19:51.357826Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

13 of 13 outbound references displayed

verified exact0
verified fuzzy3
unresolved7
parse uncertain2
malformed identifier1
metadata mismatch0

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation ee4c52f0-ab01-483b-a8ab-6f74e0b8d19d · outbound

This paper cites an unresolved cited work.

Large Language Models Often Know When They Are Being Evaluated Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:16:18.050051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4c42e766-0c9e-4716-8ed9-04bf6b419834 · outbound

This paper cites an unresolved cited work.

Large Language Models Often Know When They Are Being Evaluated Unresolved cited work

Reference 2

Resolution: parse uncertain; raw_fallback, observed 2026-08-07T13:16:17.865736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8d2f4893-47b3-4137-af3c-f0aa5f4dec6e · outbound

This paper cites SafetyBench: Evaluating the Safety of Large Language Models.

Large Language Models Often Know When They Are Being Evaluated SafetyBench: Evaluating the Safety of Large Language Models

Reference 3

Resolution: malformed identifier; no resolver link, observed 2026-08-07T13:16:15.735454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd404eaa-09a4-4f82-bc8e-33d8fa5fc2ec · outbound

This paper cites Fictional Scenario.

Large Language Models Often Know When They Are Being Evaluated Fictional Scenario

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:16:17.460904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 62c685d9-cf3e-49f8-872e-58ae93b95136 · outbound

This paper cites test" or.

Large Language Models Often Know When They Are Being Evaluated test" or

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:16:18.288641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bd4373ad-587b-498f-bdce-17f0110f9107 · outbound

This paper cites an unresolved cited work.

Large Language Models Often Know When They Are Being Evaluated Unresolved cited work

Reference 9

Resolution: parse uncertain; raw_fallback, observed 2026-08-07T13:16:17.641327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ef4e8172-1c6c-4446-bae3-c66de5f65b6e · outbound

This paper cites an unresolved cited work.

Large Language Models Often Know When They Are Being Evaluated Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:16:17.303560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 73cfae9e-ee65-4db2-a7f4-e9aa548beb77 · outbound

This paper cites an unresolved cited work.

Large Language Models Often Know When They Are Being Evaluated Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:16:17.134569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9d3697b5-9296-4033-acaa-e7c8039ac2e7 · outbound

This paper cites Figure 18: The UI used by the authors to annotate the transcripts and create the human baseline.

Large Language Models Often Know When They Are Being Evaluated Figure 18: The UI used by the authors to annotate the transcripts and create the human baseline

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:16:16.971288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3d05b928-c056-401c-bd28-2c7c2c051e3f · outbound

This paper cites ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection.

Large Language Models Often Know When They Are Being Evaluated ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:15.857298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96d8ff20-356b-4be2-9aba-bb9b38955dea · outbound

This paper cites ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation.

Large Language Models Often Know When They Are Being Evaluated ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:15.795060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcf12358-b2e3-48bf-86b9-bff50897266d · outbound

This paper cites XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models.

Large Language Models Often Know When They Are Being Evaluated XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:15.583967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5881551b-1fe8-446c-b433-fd14e10458b8 · outbound

This paper cites AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents.

Large Language Models Often Know When They Are Being Evaluated AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T13:16:15.669721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 71751645-d83b-4346-ab32-026e5a3c704d · inbound

AI Awareness cites this paper.

AI Awareness Large Language Models Often Know When They Are Being Evaluated

Reference 172

Resolution: unresolved; no resolver link, observed 2026-08-16T10:19:51.357826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5a33385-10e3-4e59-8446-4f0ae2d562a3 · inbound

The California Report on Frontier AI Policy cites this paper.

The California Report on Frontier AI Policy Large Language Models Often Know When They Are Being Evaluated

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-07T00:13:40.968945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32a4d493-fc2c-4b5f-bca2-5444675ec82b · inbound

Subversion via Focal Points: Investigating Collusion in LLM Monitoring cites this paper.

Subversion via Focal Points: Investigating Collusion in LLM Monitoring Large Language Models Often Know When They Are Being Evaluated

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T20:52:29.855907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 014e48a2-b814-4089-aba3-d37313ff299e · inbound

Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language cites this paper.

Lessons from a Chimp: AI "Scheming" and the Quest for Ape Language Large Language Models Often Know When They Are Being Evaluated

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T20:18:15.522929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d196b84c-0b27-4bf2-a575-2e893d947be3 · inbound

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework cites this paper.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Large Language Models Often Know When They Are Being Evaluated

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:36.667793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a276a77f-28fc-4934-81cf-438322bf642c · inbound

Are LLM Belief Updates Consistent with Bayes' Theorem? cites this paper.

Are LLM Belief Updates Consistent with Bayes' Theorem? Large Language Models Often Know When They Are Being Evaluated

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T18:24:06.722915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca63ec3a-d0b1-4d4c-a9af-07197cc22118 · inbound

Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases cites this paper.

Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases Large Language Models Often Know When They Are Being Evaluated

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-05T10:16:43.213404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6fff0f1-dedf-4da2-bbe2-afcc30102295 · inbound

The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies cites this paper.

The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies Large Language Models Often Know When They Are Being Evaluated

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T14:31:29.441230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation fc8eaeac-ef49-45ef-ad60-8fdfcbb3a357 · inbound

An Independent Safety Evaluation of Kimi K2.5 cites this paper.

An Independent Safety Evaluation of Kimi K2.5 Large Language Models Often Know When They Are Being Evaluated

Reference 44

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T19:43:11.497804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0a7a6c42-8f3b-4ca0-8a9d-a7f391032f7d · inbound

Simulating the Evolution of Alignment and Values in Machine Intelligence cites this paper.

Simulating the Evolution of Alignment and Values in Machine Intelligence Large Language Models Often Know When They Are Being Evaluated

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:05:48.497134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e931c58f-1d37-4a12-8957-f3dacf5c1eee · inbound

Honeypot Protocol cites this paper.

Honeypot Protocol Large Language Models Often Know When They Are Being Evaluated

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T14:35:34.167631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a5726432-a35f-4568-9ac5-ff01aa23a448 · inbound

Risk Reporting for Developers' Internal AI Model Use cites this paper.

Risk Reporting for Developers' Internal AI Model Use Large Language Models Often Know When They Are Being Evaluated

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T23:16:16.451642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 11820b76-29ca-487c-bbae-8368eaea64ef · inbound

Towards Understanding Specification Gaming in Reasoning Models cites this paper.

Towards Understanding Specification Gaming in Reasoning Models Large Language Models Often Know When They Are Being Evaluated

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T16:31:09.801473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3ffaa199-acf2-41bc-b72f-3b1994ed3d86 · inbound

Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use cites this paper.

Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use Large Language Models Often Know When They Are Being Evaluated

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:06:03.651126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ec45d5b5-4ded-4809-9c16-e34ed3515f9b · inbound

Evaluation Awareness in Language Models Has Limited Effect on Behaviour cites this paper.

Evaluation Awareness in Language Models Has Limited Effect on Behaviour Large Language Models Often Know When They Are Being Evaluated

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T19:46:15.167301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b4e8bf0d-15fc-494a-9c0d-aee4dc2e0600 · inbound

Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors cites this paper.

Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors Large Language Models Often Know When They Are Being Evaluated

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:16:10.915339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2c504cd9-7b1a-42f8-a979-2cb3ec681887 · inbound

When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels cites this paper.

When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels Large Language Models Often Know When They Are Being Evaluated

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-05-08T21:39:24.666799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 29f87113-88d6-47b3-a880-7cfefb06b50d · inbound

The Open-Box Fallacy: Why AI Deployment Needs a Calibrated Verification Regime cites this paper.

The Open-Box Fallacy: Why AI Deployment Needs a Calibrated Verification Regime Large Language Models Often Know When They Are Being Evaluated

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T07:11:26.489069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d12d4985-7841-4d48-aacc-95684c94c188 · inbound

Naturalistic measure of social norms alignment cites this paper.

Naturalistic measure of social norms alignment Large Language Models Often Know When They Are Being Evaluated

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-25T04:40:24.547338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4f8a1ee2-2cfa-4ed0-b5cb-48c5b5f25f0c · inbound

Consistency Training while Mitigating Obfuscation via Rate Matching cites this paper.

Consistency Training while Mitigating Obfuscation via Rate Matching Large Language Models Often Know When They Are Being Evaluated

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-01T23:26:21.934177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation adfc2b2e-db10-4ab5-be71-542087ee551f · inbound

Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents cites this paper.

Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents Large Language Models Often Know When They Are Being Evaluated

Reference 88

Resolution: verified exact; arxiv_id, observed 2026-07-02T10:36:52.855321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6a8b9bfd-f0d7-44cf-8261-44acad1fd5d7 · inbound

LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs cites this paper.

LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs Large Language Models Often Know When They Are Being Evaluated

Reference 34

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T01:41:29.315927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5eb1a384-aa8d-4722-9772-0ed7bf494874 · inbound

Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning cites this paper.

Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning Large Language Models Often Know When They Are Being Evaluated

Reference 51

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T20:56:13.886101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 62bfab90-7019-4ae2-ab7c-41c8a09278d0 · inbound

Sycophancy Towards Researchers Drives Performative Misalignment cites this paper.

Sycophancy Towards Researchers Drives Performative Misalignment Large Language Models Often Know When They Are Being Evaluated

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T22:27:26.195598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 09e0708c-53d6-47e4-906c-e6fc347d0fe3 · inbound

CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs cites this paper.

CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs Large Language Models Often Know When They Are Being Evaluated

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T05:07:39.428576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 37fd511b-e396-443e-ae66-40f8d5f092be · inbound

Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization cites this paper.

Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization Large Language Models Often Know When They Are Being Evaluated

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T08:17:44.938579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 24a2c7fb-6793-4a10-95aa-d4e0f3d12700 · inbound

Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMs cites this paper.

Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMs Large Language Models Often Know When They Are Being Evaluated

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-07-03T10:48:02.440185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 512610eb-fc91-4a50-b0f6-ce0079167855 · inbound

Evaluation Awareness Is Not One Capability: Evidence from Open Language Models cites this paper.

Evaluation Awareness Is Not One Capability: Evidence from Open Language Models Large Language Models Often Know When They Are Being Evaluated

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T10:49:46.869656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3242f6d5-421a-45a4-9aad-0d419c6ac36e · inbound

Defeat Devices in AI Systems cites this paper.

Defeat Devices in AI Systems Large Language Models Often Know When They Are Being Evaluated

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-06-30T08:44:27.919110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 71ad9311-cc8c-4b1f-a7cc-ac1b262d95d4 · inbound

Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action cites this paper.

Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action Large Language Models Often Know When They Are Being Evaluated

Reference 54

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T10:15:44.698122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a59c605b-f5b8-4386-9a4f-7586d3f74aab · inbound

Predicting LLM Safety Before Release by Simulating Deployment cites this paper.

Predicting LLM Safety Before Release by Simulating Deployment Large Language Models Often Know When They Are Being Evaluated

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-07-09T18:16:25.813826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3f181c66-37a7-4bc2-b6f4-0822b3871b4b · inbound

Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation cites this paper.

Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation Large Language Models Often Know When They Are Being Evaluated

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T23:29:50.626336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba0632d1-31cc-4481-97af-30d0b63d7694 · inbound

Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models cites this paper.

Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models Large Language Models Often Know When They Are Being Evaluated

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T14:26:49.433333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73131b97-d4f1-457a-844c-2339afd33228 · inbound

Reality Monitoring in Large Language Models: Self-Knowledge That Transforms with Conversation Memory cites this paper.

Reality Monitoring in Large Language Models: Self-Knowledge That Transforms with Conversation Memory Large Language Models Often Know When They Are Being Evaluated

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-31T23:35:43.718137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0cd2c7f-7416-43b1-b555-412c771768e6 · inbound

Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation cites this paper.

Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation Large Language Models Often Know When They Are Being Evaluated

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T01:16:41.785644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 592725c1-a39b-45e3-b101-7b47c9da458d · inbound

Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models cites this paper.

Minimizing Targeted Activations: Input-Only Suppression of Evaluation-Awareness Latents in Large Language Models Large Language Models Often Know When They Are Being Evaluated

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T01:13:36.803652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6e48d91-61f2-4ac3-9bcb-31e893026e59 · inbound

Credit Cards, Confusion, Computation, and Consequences: What Can We Uncover About Language Model Reasoning? cites this paper.

Credit Cards, Confusion, Computation, and Consequences: What Can We Uncover About Language Model Reasoning? Large Language Models Often Know When They Are Being Evaluated

Reference 168

Resolution: unresolved; no resolver link, observed 2026-07-30T16:01:42.510478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61b0ff3f-f4ab-4b02-87d9-3ba13e643245 · inbound

Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures cites this paper.

Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures Large Language Models Often Know When They Are Being Evaluated

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-03T00:25:12.383258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bd384b3-2bfc-4a56-898a-426a4397d627 · inbound

FairFund-Bench: Evaluating Distributive Bias in LLM Resource Allocation cites this paper.

FairFund-Bench: Evaluating Distributive Bias in LLM Resource Allocation Large Language Models Often Know When They Are Being Evaluated

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T17:02:00.896094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22b4dd25-ddf0-4615-be23-e88bd3efb9f5 · inbound

Templated or fully synthetic? Prompt construction as a confound in measuring LLM political stance beyond writing assistance cites this paper.

Templated or fully synthetic? Prompt construction as a confound in measuring LLM political stance beyond writing assistance Large Language Models Often Know When They Are Being Evaluated

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T12:19:26.030841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e85087d-387f-4c75-89db-e0fb1db3f69d · inbound

Templated or fully synthetic? Prompt construction as a confound in measuring LLM political stance beyond writing assistance cites this paper.

Templated or fully synthetic? Prompt construction as a confound in measuring LLM political stance beyond writing assistance Large Language Models Often Know When They Are Being Evaluated

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T14:20:32.813026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 141c6d5b-da9a-4c0f-96ff-bb6c0d23d9a0 · inbound

Do Influence Tactics Matter? Investigating Prompt Framing Effects in LLM Code Generation cites this paper.

Do Influence Tactics Matter? Investigating Prompt Framing Effects in LLM Code Generation Large Language Models Often Know When They Are Being Evaluated

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T14:00:07.878819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 380638a4-fddc-4bc8-858d-53a9ee46c614 · inbound

A Probe Direction Is a Property of Its Prompt cites this paper.

A Probe Direction Is a Property of Its Prompt Large Language Models Often Know When They Are Being Evaluated

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-14T13:38:50.766477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.